In medical care, side effect trial and error processes are utilized for the discovery of hidden reasons for ailments and the determination of conditions. In our exploration, we used a crossbreed strategy to refine our optimal model, improving the Pearson relationship for highlight choice purposes. The underlying stage included the choice of ideal models through a careful survey of the current writing. Hence, our proposed half-and-half model incorporated a blend of these models. The base classifiers utilized included XGBoost, Arbitrary Woods, Strategic Relapse, AdaBoost, and the Crossover model classifiers, while the Meta classifier was the Irregular Timberland classifier. The essential target of this examination was to evaluate the best AI grouping techniques and decide the best classifier concerning accuracy. This approach resolved the issue of overfitting and accomplished the most elevated level of exactness. The essential focal point of the assessment was precision, and we introduced a far-reaching examination of the significant writing in even configuration. To carry out our methodology, we used four top-performing AI models and fostered another model named" half and half," utilizing the UCI Persistent Kidney Disappointment dataset for prescient purposes. In our experiment, we found out that the AI model XGBoost classifier gains almost 94% accuracy, a random forest gains 93% accuracy, Logistic Regression about 90% accuracy, AdaBoost gains 91% accuracy, and our proposed new model named hybrid gains the highest 95% accuracy, and performance of Hybrid model is best on this equivalent dataset. Various noticeable AI models have been utilized to foresee the event of persistent kidney disappointment (CKF). These models incorporate Naïve Bayes, Random Forest, Decision Tree, Support Vector Machine, K-nearest neighbor, LDA (Linear Discriminant Analysis), GB (Gradient Boosting), and neural networks. In our examination, we explicitly used XGBoost, AdaBoost, Logistic Regression, Random Forest, and Hybrid models with the equivalent dataset of highlights to analyze their accuracy scores.